Phase 2.6.1: co_occurrence_edges migration - build_co_occurrence_edges_from_qdrant() - Qdrant embeddings → frame grouping → YOLO objects - Result: 6679 edges (vs 6701 PostgreSQL) Phase 2.6.2: face_face_edges migration - build_face_face_edges_from_qdrant() - Qdrant embeddings → frame grouping → face pairs - mutual_gaze detection preserved - Result: 6 edges (exact match) Phase 2.6.3: speaker_face_edges migration - build_speaker_face_edges_from_qdrant() - Qdrant embeddings → trace_id frame ranges - SPEAKS_AS edge creation Architecture: - All edges use Qdrant payload (no face_detections queries) - PostgreSQL fallback for empty Qdrant - Estimated 3.6x performance improvement Testing: - Playground (3003): ✓ All Phase 2.6 logs verified - Edge counts: ✓ Close match with PostgreSQL - Fallback: ✓ Working Docs: - docs_v1.0/DESIGN/TKG_PHASE2_6_EDGES_MIGRATION.md - docs_v1.0/M4_workspace/2026-06-21_phase2_6_test.md
77 lines
1.9 KiB
Python
77 lines
1.9 KiB
Python
#!/opt/homebrew/bin/python3.11
|
|
"""Backfill face_id for existing face_detections rows using trace_id.
|
|
|
|
face_id is generated as 'face_{trace_id}' for each unique trace.
|
|
This covers past data where face_id was never written.
|
|
"""
|
|
|
|
import os
|
|
import psycopg2
|
|
|
|
DB_URL = os.environ.get("DATABASE_URL", "postgresql://accusys@localhost:5432/momentry")
|
|
SCHEMA = os.environ.get("MOMENTRY_DB_SCHEMA", "dev")
|
|
|
|
|
|
def get_conn():
|
|
return psycopg2.connect(DB_URL)
|
|
|
|
|
|
def backfill_by_trace(file_uuid: str, schema: str = SCHEMA) -> int:
|
|
"""Set face_id = 'face_{trace_id}' for all rows with NULL face_id and non-NULL trace_id."""
|
|
conn = get_conn()
|
|
cur = conn.cursor()
|
|
|
|
cur.execute(
|
|
f"""
|
|
UPDATE {schema}.face_detections
|
|
SET face_id = 'face_' || trace_id::text
|
|
WHERE file_uuid = %s
|
|
AND face_id IS NULL
|
|
AND trace_id IS NOT NULL
|
|
""",
|
|
(file_uuid,),
|
|
)
|
|
updated = cur.rowcount
|
|
conn.commit()
|
|
cur.close()
|
|
conn.close()
|
|
return updated
|
|
|
|
|
|
def main():
|
|
conn = get_conn()
|
|
cur = conn.cursor()
|
|
|
|
# Count rows that need backfill
|
|
cur.execute(
|
|
f"""SELECT COUNT(*) FROM {SCHEMA}.face_detections
|
|
WHERE face_id IS NULL AND trace_id IS NOT NULL"""
|
|
)
|
|
total_rows = cur.fetchone()[0]
|
|
|
|
cur.execute(
|
|
f"""SELECT DISTINCT file_uuid FROM {SCHEMA}.face_detections
|
|
WHERE face_id IS NULL AND trace_id IS NOT NULL"""
|
|
)
|
|
uuids = [row[0] for row in cur.fetchall()]
|
|
cur.close()
|
|
conn.close()
|
|
|
|
if not uuids:
|
|
print("No rows need backfill (all face_id already set or no trace_id).")
|
|
return
|
|
|
|
print(f"Found {total_rows} rows across {len(uuids)} files to backfill")
|
|
|
|
total_all = 0
|
|
for uuid in uuids:
|
|
count = backfill_by_trace(uuid)
|
|
total_all += count
|
|
print(f" [{uuid}] updated {count} rows")
|
|
|
|
print(f"\nDone: {len(uuids)} files, {total_all} rows updated")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|